Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aneja5/forge-skills/accessibilitynpx skills add aneja5/forge-skills --skill accessibilitygit clone --depth 1 https://github.com/aneja5/forge-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aneja5/forge-skills/accessibility)<a href="https://agentmods.dev/skills/aneja5/forge-skills/accessibility"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/accessibility.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.01708 |
| Opus 5 | $0.00024 | $0.00854 |
| Sonnet 5 | $0.00010 | $0.00342 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
accessibility scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility
Overview
Establish WCAG AA as the baseline floor for every UI surface — before it ships. Output is .forge/accessibility.md — the semantic-HTML rules, the ARIA usage policy, keyboard navigation requirements, focus management rules, contrast policy, reduced-motion respect, and the screen-reader testing checklist. Pairs with design-system (which defines the visual tokens that meet contrast) and interaction-patterns (which defines the keyboard and focus contract).
When to Use
- A UI surface is going to production and there's no accessibility audit
- The product ships to EU, government, healthcare, or education customers (legal requirement)
- A user reports that they can't use a feature with keyboard or screen reader
- A new component category is being added (modal, drawer, command palette) and focus management is unclear
- An existing UI is being audited and ARIA usage looks suspicious
When NOT to Use
- Internal CLI tools or backend services with no UI
- Throwaway prototypes that will never ship
- Single one-line copy changes that don't touch interaction or structure
Common Rationalizations
| Thought | Reality |
|---|---|
| "Accessibility is a nice-to-have" | It's a legal requirement in most markets (ADA in US, EAA in EU, AODA in Canada) and a usability requirement everywhere. |
| "We'll add it later" | Retrofitting a11y costs 10x building it in. Every component pattern picked without a11y becomes a refactor. |
| "Our users don't need it" | You don't know that — assistive tech use is often invisible. ~20% of users have a disability in some form. |
| "ARIA fixes everything" | ARIA overuse is worse than no ARIA. Native semantic HTML always beats <div role="button">. |
| "Just make the visible thing look right" | Screen readers see structure, not pixels. A visually-correct page can be unusable with VoiceOver. |
| "Color is enough to signal state" | Colorblind users can't see red-vs-green; every meaningful color needs a text or icon backup. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 133 lines · 49 tokens per session scan A c9e409fb14df
accessibility is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,708 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.